Annie Zhao
Software Engineer at BAE Systems, Inc.
San Diego, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAnnie Zhao is a software engineer based in San Diego with a decade of experience building machine learning and production software, currently at BAE Systems. She brings practical ML engineering expertise from her Azavea fellowship and open-source contributions to Raster Vision—improving preprocessing, evaluation, and integrating DenseNet models for satellite and aerial imagery tasks. Comfortable bridging technical and human-facing roles, she has a background mentoring students, running live technical production as a master electrician, and supporting nonprofit operations. Annie combines a collaborative, creative mindset with rigorous engineering habits like unit testing and reproducible dataset normalization, and she’s driven to improve communication while exploring the evolving landscape of AI and robotics.
10 years of coding experience
1 year of employment as a software developer
3.97/4.0 (unweighted), 3.97/4.0 (unweighted) at Portsmouth Abbey SchoolBachelor's degree, Computer Science and Political Science, Bachelor's degree, Computer Science and Political Science at Swarthmore College
English, Chinese
Github Skills (17)
pytorch10
python10
evaluation10
data-science10
machine-learning10
normalization10
eval10
deep-learning10
computer-vision10
image-augmentation10
unit-testing9
classification9
tensorflow9
keras9
object-detection8
Programming languages (4)
Github contributions (5)
azavea/raster-vision
Jun 2017 - Aug 2017
An open source library and framework for deep learning on satellite and aerial imagery.
Role in this project:
ML Engineer & Data Scientist
ML Engineer & Data ScientistContributions:25 commits, 22 PRs, 165 pushes in 1 month
Contributions summary:Annie made significant contributions to the `raster-vision` project, primarily focused on improving the image preprocessing and model evaluation pipelines. They implemented the ability to save normalization parameters for datasets, ensuring consistency across training runs and wrote unit tests for these changes. Furthermore, the user added test data and made improvements to the model evaluation process by providing more detailed scoring outputs, along with augmented image processing for the testing phase. They also integrated new DenseNet models and configured the project to utilize learning rate decay.
pytorchgeospatialsemantic-segmentationdeep-learningsatellite
citerana/citerana.github.io
Apr 2016 - Mar 2018
Contributions:23 pushes, 1 branch in 1 year 11 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.